对比度学习依赖于假设正对包含相关视图，例如，视频的图像或视频的共同发生的多峰信号，其共享关于实例的某些基础信息。但如果违反了这个假设怎么办？该文献表明，对比学学习在存在嘈杂的视图中产生次优表示，例如，没有明显共享信息的假正对。在这项工作中，我们提出了一种新的对比损失函数，这是对嘈杂的观点的强大。我们通过显示嘈杂二进制分类的强大对称损失的连接提供严格的理论理由，并通过基于Wassersein距离测量来建立新的对比界限进行新的对比。拟议的损失是完全的方式无话无双，并且对Innoconce损失的更换简单的替代品，这使得适用于现有的对比框架。我们表明，我们的方法提供了在展示各种现实世界噪声模式的图像，视频和图形对比学习基准上的一致性改进。

了解深度神经网络的泛化是深度学习中最重要的任务之一。虽然已经取得了很大进展，但理论错误界限仍然往往与经验观察结果不同。在这项工作中，我们开发基于保证金的泛化界，其中边距是在从训练分布中采样的独立随机子集之间的最佳运输成本标准化。特别地，最佳运输成本可以被解释为方差的概念，其捕获学习特征空间的结构特性。我们的界限强大地预测了在大规模数据集上给定培训数据和网络参数的泛化误差。从理论上讲，我们表明特征的浓度和分离在泛化中起着至关重要的作用，支持文献中的经验结果。该代码可用于\ url {https:/github.com/chingyaoc/kv-margin}。

A prominent technique for self-supervised representation learning has been to contrast semantically similar and dissimilar pairs of samples. Without access to labels, dissimilar (negative) points are typically taken to be randomly sampled datapoints, implicitly accepting that these points may, in reality, actually have the same label. Perhaps unsurprisingly, we observe that sampling negative examples from truly different labels improves performance, in a synthetic setting where labels are available. Motivated by this observation, we develop a debiased contrastive objective that corrects for the sampling of same-label datapoints, even without knowledge of the true labels. Empirically, the proposed objective consistently outperforms the state-of-the-art for representation learning in vision, language, and reinforcement learning benchmarks. Theoretically, we establish generalization bounds for the downstream classification task.

Optimization in multi-task learning (MTL) is more challenging than single-task learning (STL), as the gradient from different tasks can be contradictory. When tasks are related, it can be beneficial to share some parameters among them (cooperation). However, some tasks require additional parameters with expertise in a specific type of data or discrimination (specialization). To address the MTL challenge, we propose Mod-Squad, a new model that is Modularized into groups of experts (a 'Squad'). This structure allows us to formalize cooperation and specialization as the process of matching experts and tasks. We optimize this matching process during the training of a single model. Specifically, we incorporate mixture of experts (MoE) layers into a transformer model, with a new loss that incorporates the mutual dependence between tasks and experts. As a result, only a small set of experts are activated for each task. This prevents the sharing of the entire backbone model between all tasks, which strengthens the model, especially when the training set size and the number of tasks scale up. More interestingly, for each task, we can extract the small set of experts as a standalone model that maintains the same performance as the large model. Extensive experiments on the Taskonomy dataset with 13 vision tasks and the PASCAL-Context dataset with 5 vision tasks show the superiority of our approach.

We present a new method for generating controllable, dynamically responsive, and photorealistic human animations. Given an image of a person, our system allows the user to generate Physically plausible Upper Body Animation (PUBA) using interaction in the image space, such as dragging their hand to various locations. We formulate a reinforcement learning problem to train a dynamic model that predicts the person's next 2D state (i.e., keypoints on the image) conditioned on a 3D action (i.e., joint torque), and a policy that outputs optimal actions to control the person to achieve desired goals. The dynamic model leverages the expressiveness of 3D simulation and the visual realism of 2D videos. PUBA generates 2D keypoint sequences that achieve task goals while being responsive to forceful perturbation. The sequences of keypoints are then translated by a pose-to-image generator to produce the final photorealistic video.

This paper describes the ESPnet Unsupervised ASR Open-source Toolkit (EURO), an end-to-end open-source toolkit for unsupervised automatic speech recognition (UASR). EURO adopts the state-of-the-art UASR learning method introduced by the Wav2vec-U, originally implemented at FAIRSEQ, which leverages self-supervised speech representations and adversarial training. In addition to wav2vec2, EURO extends the functionality and promotes reproducibility for UASR tasks by integrating S3PRL and k2, resulting in flexible frontends from 27 self-supervised models and various graph-based decoding strategies. EURO is implemented in ESPnet and follows its unified pipeline to provide UASR recipes with a complete setup. This improves the pipeline's efficiency and allows EURO to be easily applied to existing datasets in ESPnet. Extensive experiments on three mainstream self-supervised models demonstrate the toolkit's effectiveness and achieve state-of-the-art UASR performance on TIMIT and LibriSpeech datasets. EURO will be publicly available at https://github.com/espnet/espnet, aiming to promote this exciting and emerging research area based on UASR through open-source activity.

Contour-based instance segmentation methods include one-stage and multi-stage schemes. These approaches achieve remarkable performance. However, they have to define plenty of points to segment precise masks, which leads to high complexity. We follow this issue and present a single-shot method, called \textbf{VeinMask}, for achieving competitive performance in low design complexity. Concretely, we observe that the leaf locates coarse margins via major veins and grows minor veins to refine twisty parts, which makes it possible to cover any objects accurately. Meanwhile, major and minor veins share the same growth mode, which avoids modeling them separately and ensures model simplicity. Considering the superiorities above, we propose VeinMask to formulate the instance segmentation problem as the simulation of the vein growth process and to predict the major and minor veins in polar coordinates. Besides, centroidness is introduced for instance segmentation tasks to help suppress low-quality instances. Furthermore, a surroundings cross-correlation sensitive (SCCS) module is designed to enhance the feature expression by utilizing the surroundings of each pixel. Additionally, a Residual IoU (R-IoU) loss is formulated to supervise the regression tasks of major and minor veins effectively. Experiments demonstrate that VeinMask performs much better than other contour-based methods in low design complexity. Particularly, our method outperforms existing one-stage contour-based methods on the COCO dataset with almost half the design complexity.

With the increasing variations of face presentation attacks, model generalization becomes an essential challenge for a practical face anti-spoofing system. This paper presents a generalized face anti-spoofing framework that consists of three tasks: depth estimation, face parsing, and live/spoof classification. With the pixel-wise supervision from the face parsing and depth estimation tasks, the regularized features can better distinguish spoof faces. While simulating domain shift with meta-learning techniques, the proposed one-side triplet loss can further improve the generalization capability by a large margin. Extensive experiments on four public datasets demonstrate that the proposed framework and training strategies are more effective than previous works for model generalization to unseen domains.

Existing object detection methods are bounded in a fixed-set vocabulary by costly labeled data. When dealing with novel categories, the model has to be retrained with more bounding box annotations. Natural language supervision is an attractive alternative for its annotation-free attributes and broader object concepts. However, learning open-vocabulary object detection from language is challenging since image-text pairs do not contain fine-grained object-language alignments. Previous solutions rely on either expensive grounding annotations or distilling classification-oriented vision models. In this paper, we propose a novel open-vocabulary object detection framework directly learning from image-text pair data. We formulate object-language alignment as a set matching problem between a set of image region features and a set of word embeddings. It enables us to train an open-vocabulary object detector on image-text pairs in a much simple and effective way. Extensive experiments on two benchmark datasets, COCO and LVIS, demonstrate our superior performance over the competing approaches on novel categories, e.g. achieving 32.0% mAP on COCO and 21.7% mask mAP on LVIS. Code is available at: https://github.com/clin1223/VLDet.

Knowledge graph data are prevalent in real-world applications, and knowledge graph neural networks (KGNNs) are essential techniques for knowledge graph representation learning. Although KGNN effectively models the structural information from knowledge graphs, these frameworks amplify the underlying data bias that leads to discrimination towards certain groups or individuals in resulting applications. Additionally, as existing debiasing approaches mainly focus on the entity-wise bias, eliminating the multi-hop relational bias that pervasively exists in knowledge graphs remains an open question. However, it is very challenging to eliminate relational bias due to the sparsity of the paths that generate the bias and the non-linear proximity structure of knowledge graphs. To tackle the challenges, we propose Fair-KGNN, a KGNN framework that simultaneously alleviates multi-hop bias and preserves the proximity information of entity-to-relation in knowledge graphs. The proposed framework is generalizable to mitigate the relational bias for all types of KGNN. We develop two instances of Fair-KGNN incorporating with two state-of-the-art KGNN models, RGCN and CompGCN, to mitigate gender-occupation and nationality-salary bias. The experiments carried out on three benchmark knowledge graph datasets demonstrate that the Fair-KGNN can effectively mitigate unfair situations during representation learning while preserving the predictive performance of KGNN models.